Transform architecture for multiple neurosynaptic core circuits

摘要

Embodiments of the present invention provide a method for feature extraction using multiple neurosynaptic core circuits including one or more input core circuits for receiving input and one or more output core circuits for generating output. The method comprises receiving a set of input data via the input core circuits, and extracting a first set of features from the input data using the input core circuits. Each feature of the first set of features is based on a subset of the input data. The method further comprises reordering the first set of features using the input core circuits, and generating a second set of features by combining the reordered first set of features using the output core circuits. The second set of features comprises a set of features with reduced correlation. Each feature of the second set of features is based on the entirety of said set of input data.

主权项

1. A method for feature extraction using multiple neurosynaptic core circuits including one or more input core circuits for receiving input and one or more output core circuits for generating output, comprising:
receiving a set of input data via said one or more input core circuits; extracting a first set of features from said set of input data using said one or more input core circuits, wherein each feature of said first set of features is based on a subset of said set of input data; reordering said first set of features using said one or more input core circuits; and generating a second set of features by combining said reordered first set of features using said one or more output core circuits, wherein said second set of features comprises a set of features with reduced correlation, and wherein each feature of said second set of features is based on the entirety of said set of input data.